Earthquake Prediction Project

Importing the necessary libraries

import numpy as np
import pandas as pd
import requests
from sklearn import preprocessing
import matplotlib.pyplot as plt
import seaborn as sns
from pandas.plotting import scatter_matrix
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler
import time

Linking the csv dataset file

Dataset Link - https://drive.google.com/drive/folders/1b4IyWfUzbDgOvuW_W7rOSEeTpBN53Mlf

df = pd.read_csv(r'C:\Users\arjun\OneDrive\Desktop\2023 Sept Fall 3rd sem\Predictive Analytics\Earthquake_dataset_Arjun\earthquake1.csv')

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 24007 entries, 0 to 24006
Data columns (total 17 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   id         24007 non-null  float64
 1   date       24007 non-null  object 
 2   time       24007 non-null  object 
 3   lat        24007 non-null  float64
 4   long       24007 non-null  float64
 5   country    24007 non-null  object 
 6   city       11754 non-null  object 
 7   area       12977 non-null  object 
 8   direction  10062 non-null  object 
 9   dist       10062 non-null  float64
 10  depth      24007 non-null  float64
 11  xm         24007 non-null  float64
 12  md         24007 non-null  float64
 13  richter    24007 non-null  float64
 14  mw         5003 non-null   float64
 15  ms         24007 non-null  float64
 16  mb         24007 non-null  float64
dtypes: float64(11), object(6)
memory usage: 3.1+ MB

df.describe()

	id	lat	long	dist	depth	xm	md	richter	mw	ms	mb
count	2.400700e+04	24007.000000	24007.000000	10062.000000	24007.000000	24007.000000	24007.000000	24007.000000	5003.000000	24007.000000	24007.000000
mean	1.991982e+13	37.929474	30.773229	3.175015	18.491773	4.056038	1.912346	2.196826	4.478973	0.677677	1.690561
std	2.060396e+11	2.205605	6.584596	4.715461	23.218553	0.574085	2.059780	2.081417	1.048085	1.675708	2.146108
min	1.910000e+13	29.740000	18.340000	0.100000	0.000000	3.500000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	1.980000e+13	36.190000	26.195000	1.400000	5.000000	3.600000	0.000000	0.000000	4.100000	0.000000	0.000000
50%	2.000000e+13	38.200000	28.350000	2.300000	10.000000	3.900000	0.000000	3.500000	4.700000	0.000000	0.000000
75%	2.010000e+13	39.360000	33.855000	3.600000	22.400000	4.400000	3.800000	4.000000	5.000000	0.000000	4.100000
max	2.020000e+13	46.350000	48.000000	95.400000	225.000000	7.900000	7.400000	7.200000	7.700000	7.900000	7.100000

df.shape

(24007, 17)

df.head()

	id	date	time	lat	long	country	city	area	direction	dist	depth	xm	md	richter	mw	ms	mb
0	2.000000e+13	2003.05.20	12:17:44 AM	39.04	40.38	turkey	bingol	baliklicay	west	0.1	10.0	4.1	4.1	0.0	NaN	0.0	0.0
1	2.010000e+13	2007.08.01	12:03:08 AM	40.79	30.09	turkey	kocaeli	bayraktar_izmit	west	0.1	5.2	4.0	3.8	4.0	NaN	0.0	0.0
2	1.980000e+13	1978.05.07	12:41:37 AM	38.58	27.61	turkey	manisa	hamzabeyli	south_west	0.1	0.0	3.7	0.0	0.0	NaN	0.0	3.7
3	2.000000e+13	1997.03.22	12:31:45 AM	39.47	36.44	turkey	sivas	kahvepinar_sarkisla	south_west	0.1	10.0	3.5	3.5	0.0	NaN	0.0	0.0
4	2.000000e+13	2000.04.02	12:57:38 AM	40.80	30.24	turkey	sakarya	meseli_serdivan	south_west	0.1	7.0	4.3	4.3	0.0	NaN	0.0	0.0

df.columns

Index(['id', 'date', 'time', 'lat', 'long', 'country', 'city', 'area',
       'direction', 'dist', 'depth', 'xm', 'md', 'richter', 'mw', 'ms', 'mb'],
      dtype='object')

Data Preprocessing

df = df.drop('id',axis=1)

import datetime
import time
import pandas as pd

timestamp = []

for d, t in zip(df['date'], df['time']):
    try:
        ts = datetime.datetime.strptime(d+' '+t, '%Y.%m.%d %I:%M:%S %p')
        timestamp.append(time.mktime(ts.timetuple()))
    except OverflowError:
        timestamp.append(None)  # or any other value that indicates an error

timeStamp = pd.Series(timestamp)
df['Timestamp'] = timeStamp.values
final_data = df.drop(['date', 'time'], axis=1)
df = final_data
df = df.dropna(subset=['Timestamp'])  # Drop rows with invalid timestamps
df.head()

	lat	long	country	city	area	direction	dist	depth	xm	md	richter	mw	ms	mb	Timestamp
0	39.04	40.38	turkey	bingol	baliklicay	west	0.1	10.0	4.1	4.1	0.0	NaN	0.0	0.0	1.053401e+09
1	40.79	30.09	turkey	kocaeli	bayraktar_izmit	west	0.1	5.2	4.0	3.8	4.0	NaN	0.0	0.0	1.185937e+09
2	38.58	27.61	turkey	manisa	hamzabeyli	south_west	0.1	0.0	3.7	0.0	0.0	NaN	0.0	3.7	2.633605e+08
3	39.47	36.44	turkey	sivas	kahvepinar_sarkisla	south_west	0.1	10.0	3.5	3.5	0.0	NaN	0.0	0.0	8.590015e+08
4	40.80	30.24	turkey	sakarya	meseli_serdivan	south_west	0.1	7.0	4.3	4.3	0.0	NaN	0.0	0.0	9.546479e+08

df.dtypes

lat          float64
long         float64
country       object
city          object
area          object
direction     object
dist         float64
depth        float64
xm           float64
md           float64
richter      float64
mw           float64
ms           float64
mb           float64
Timestamp    float64
dtype: object

# Data Encoding
label_encoder = preprocessing.LabelEncoder() 
for col in df.columns:
    if df[col].dtype == 'object':
      label_encoder.fit(df[col])
      df[col] = label_encoder.transform(df[col])
df.dtypes

C:\Users\arjun\AppData\Local\Temp\ipykernel_18248\1335032553.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[col] = label_encoder.transform(df[col])
C:\Users\arjun\AppData\Local\Temp\ipykernel_18248\1335032553.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[col] = label_encoder.transform(df[col])
C:\Users\arjun\AppData\Local\Temp\ipykernel_18248\1335032553.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[col] = label_encoder.transform(df[col])
C:\Users\arjun\AppData\Local\Temp\ipykernel_18248\1335032553.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[col] = label_encoder.transform(df[col])

lat          float64
long         float64
country        int32
city           int32
area           int32
direction      int32
dist         float64
depth        float64
xm           float64
md           float64
richter      float64
mw           float64
ms           float64
mb           float64
Timestamp    float64
dtype: object

df.isnull().sum()

lat              0
long             0
country          0
city             0
area             0
direction        0
dist         12250
depth            0
xm               0
md               0
richter          0
mw           18681
ms               0
mb               0
Timestamp        0
dtype: int64

# Imputing Missing Values with Mean
si=SimpleImputer(missing_values = np.nan, strategy="mean")
si.fit(df[["dist","mw"]])
df[["dist","mw"]] = si.transform(df[["dist","mw"]])
df.isnull().sum()

C:\Users\arjun\AppData\Local\Temp\ipykernel_18248\1255669323.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[["dist","mw"]] = si.transform(df[["dist","mw"]])

lat          0
long         0
country      0
city         0
area         0
direction    0
dist         0
depth        0
xm           0
md           0
richter      0
mw           0
ms           0
mb           0
Timestamp    0
dtype: int64

Data Visualization

import plotly.express as px
px.scatter(df, x='richter',y='xm', color="direction")

plt.figure(figsize=(7,7))
sns.histplot(data=df, x='depth', hue='direction',palette = 'Accent')
plt.show()

plt.figure(figsize=(7,7))
df[['lat','long']].hist()
plt.show()

<Figure size 700x700 with 0 Axes>

plt.figure(figsize=(10,10))
sns.distplot(df.xm)

C:\Users\arjun\AppData\Local\Temp\ipykernel_18248\3879995472.py:2: UserWarning:



`distplot` is a deprecated function and will be removed in seaborn v0.14.0.

Please adapt your code to use either `displot` (a figure-level function with
similar flexibility) or `histplot` (an axes-level function for histograms).

For a guide to updating your code to use the new functions, please see
https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751

<Axes: xlabel='xm', ylabel='Density'>

plt.figure(figsize=(15,10))
sns.barplot(x=df['xm'], y=df['ms'])
plt.xlabel('xm')
plt.ylabel('ms')

Text(0, 0.5, 'ms')

plt.scatter(df.depth, df.xm)
plt.xlabel("Depth")
plt.ylabel("xm")
plt.show()

plt.scatter(df.depth, df.mb)
plt.xlabel("Depth")
plt.ylabel("Magnitude body")
plt.show()

plt.scatter(df.dist, df.depth)
plt.xlabel("Area affected")
plt.ylabel("Depth")
plt.show()

plt.scatter(df.dist, df.depth)
plt.xlabel("Area affected")
plt.ylabel("xm")
plt.show()

Correlation between Attributes

most_correlated = df.corr()['xm'].sort_values(ascending=False)
most_correlated

xm           1.000000
mb           0.520944
ms           0.466182
richter      0.279865
mw           0.279404
depth        0.248506
area         0.111337
city         0.104095
long         0.091117
direction    0.085171
dist         0.001002
lat         -0.043337
country     -0.045640
md          -0.101287
Timestamp   -0.194235
Name: xm, dtype: float64

plt.figure(figsize=(20,20))
dataplot=sns.heatmap(df.corr(),annot=True)
plt.show()

Normalization of data

# Using MinMaxScaler
scaler = preprocessing.MinMaxScaler()
d = scaler.fit_transform(df)
df = pd.DataFrame(d, columns=df.columns)
df.head()

	lat	long	country	city	area	direction	dist	depth	xm	md	richter	mw	ms	mb	Timestamp
0	0.559904	0.743088	0.76	0.173913	0.116178	0.875	0.0	0.048077	0.150	0.554054	0.000000	0.553294	0.0	0.000000	0.701575
1	0.665262	0.396156	0.76	0.608696	0.132893	0.875	0.0	0.025000	0.125	0.513514	0.571429	0.553294	0.0	0.000000	0.789847
2	0.532210	0.312542	0.76	0.673913	0.459761	0.750	0.0	0.000000	0.050	0.000000	0.000000	0.553294	0.0	0.544118	0.175393
3	0.585792	0.610249	0.76	0.869565	0.511762	0.750	0.0	0.048077	0.000	0.472973	0.000000	0.553294	0.0	0.000000	0.572101
4	0.665864	0.401214	0.76	0.804348	0.688609	0.750	0.0	0.033654	0.200	0.581081	0.000000	0.553294	0.0	0.000000	0.635804

Splitting the Dataset

y=np.array(df['xm']) 
X=np.array(df.drop('xm',axis=1))
from sklearn.model_selection import train_test_split  
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=2) 

Creating Models

1. Linear Regression

from sklearn.linear_model import LinearRegression 
start1 = time.time() 
linear=LinearRegression() 
linear.fit(X_train,y_train) 
ans1 = linear.predict(X_test)
end1 = time.time()
t1 = end1-start1

accuracy1=linear.score(X_test,y_test) 
print("Accuracy of Linear Regression model is:",accuracy1)

Accuracy of Linear Regression model is: 0.63134131503029

from sklearn import metrics
print("Linear Regression")
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, ans1))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, ans1))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, ans1)))

Linear Regression
Mean Absolute Error: 0.05878246463205686
Mean Squared Error: 0.00625827169726636
Root Mean Squared Error: 0.07910923901331854

plt.plot(y_test, ans1, 'o') 
m, b = np.polyfit(y_test,ans1, 1) 
plt.plot(y_test, m*y_test + b) 
plt.xlabel("Actual Magnitude")
plt.ylabel("Predicted Magnitude")

Text(0, 0.5, 'Predicted Magnitude')

2. Decision Tree

from sklearn.tree import DecisionTreeRegressor
start2 = time.time() 
regressor = DecisionTreeRegressor(random_state = 40) 
regressor.fit(X_train,y_train)
ans2 = regressor.predict(X_test)
end2 = time.time()
t2 = end2-start2

accuracy2=regressor.score(X_test,y_test) 
print("Accuracy of Decision Tree model is:",accuracy2)

Accuracy of Decision Tree model is: 0.9932960893884235

print("Decision Tree")
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, ans2))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, ans2))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, ans2)))

Decision Tree
Mean Absolute Error: 0.0006909999621372331
Mean Squared Error: 0.00011380416561969702
Root Mean Squared Error: 0.010667903525046383

3. KNN Model

from sklearn.neighbors import KNeighborsRegressor
start3 = time.time() 
knn = KNeighborsRegressor(n_neighbors=6)
knn.fit(X_train, y_train)
ans3 = knn.predict(X_test)
end3 = time.time()
t3 = end3-start3

accuracy3=knn.score(X_test,y_test) 
print("Accuracy of KNN model is:",accuracy3)

Accuracy of KNN model is: 0.8457466919393031

print("KNN Model")
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, ans3))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, ans3))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, ans3)))

KNN Model
Mean Absolute Error: 0.03305598677318794
Mean Squared Error: 0.002618571462992348
Root Mean Squared Error: 0.051171979275696854

import random
info = {}
for i in range(10):
  k = random.randint(2,10) 
  startk = time.time()
  knn = KNeighborsRegressor(n_neighbors=k)
  knn.fit(X_train, y_train)
  ans3 = knn.predict(X_test)
  endk = time.time()
  tk = endk-startk
  acc3=knn.score(X_test,y_test) 
  info[k] = [acc3,tk]

for i in info:
  print("for k =",i,": accuracy =",info[i][0])

for k = 4 : accuracy = 0.8559118607470738
for k = 9 : accuracy = 0.8334625255508568
for k = 8 : accuracy = 0.8384577534478264
for k = 6 : accuracy = 0.8457466919393031
for k = 5 : accuracy = 0.8519381145638621
for k = 10 : accuracy = 0.8296048410841246
for k = 7 : accuracy = 0.8425261199362686

x = list(info.keys())
yacc = []
for i in info:
  yacc.append(info[i][0])
plt.plot(x, yacc, 'o', color='black');
plt.xlabel("k value")
plt.ylabel("accuracy");
plt.title("Accuracy for different values of k")

Text(0.5, 1.0, 'Accuracy for different values of k')

yt = []
for i in info:
  yt.append(info[i][1])
plt.plot(x, yt, 'o', color='black');
plt.xlabel("k value")
plt.ylabel("execution time");
plt.title("Execution time for different values of k")

Text(0.5, 1.0, 'Execution time for different values of k')

Comparison Graphs

1. Accuracy

models = ["linear regression","decision tree","knn"]
accuracies = [accuracy1,accuracy2,accuracy3]

plt.bar(models, accuracies, color ='maroon',
        width = 0.25)
plt.xlabel("Models")
plt.ylabel("Accuracies")
plt.title("Accuracy Comparison Graph")

Text(0.5, 1.0, 'Accuracy Comparison Graph')

2. Execution Time

times = [t1,t2,t3]
plt.bar(models, times, color ='maroon',
        width = 0.25)
plt.xlabel("Models")
plt.ylabel("Execution Time")
plt.title("Execution Time Comparison Graph")

Text(0.5, 1.0, 'Execution Time Comparison Graph')